初始化项目，由ModelHub XC社区提供模型
Model: Polygl0t/GigaVerbo-v2-ablation-EDU-Synth-1.5B Source: Original Platform
This commit is contained in:
ModelHub XC
47
.gitattributes
vendored
Normal file
47
.gitattributes
vendored
Normal file
@@ -0,0 +1,47 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
calame.png filter=lfs diff=lfs merge=lfs -text
|
||||
arc.png filter=lfs diff=lfs merge=lfs -text
|
||||
learning_curves.png filter=lfs diff=lfs merge=lfs -text
|
||||
lambada.png filter=lfs diff=lfs merge=lfs -text
|
||||
hellaswag.png filter=lfs diff=lfs merge=lfs -text
|
||||
global_piqa.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/arc.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/calame.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/gigaverbo_v2_ablation_comparison.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/global_piqa.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/hellaswag.png filter=lfs diff=lfs merge=lfs -text
|
||||
.plots/lambada.png filter=lfs diff=lfs merge=lfs -text
|
||||
3
.plots/arc.png
Normal file
3
.plots/arc.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26bc7702ccffb93a074956bbb9ba2c6bc485a2d8070c450857b53e0892d805e9
|
||||
size 370435
|
||||
3
.plots/calame.png
Normal file
3
.plots/calame.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:71d3211ed7dc9cdf9480bfbecad6271a1d38bdeebece69d0823794097b4b03e4
|
||||
size 345577
|
||||
3
.plots/gigaverbo_v2_ablation_comparison.png
Normal file
3
.plots/gigaverbo_v2_ablation_comparison.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f51024b91d527d94fca832b42765f635ac9ee07596bc4a1083245b8629437dff
|
||||
size 317949
|
||||
3
.plots/global_piqa.png
Normal file
3
.plots/global_piqa.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8e3662daa95bd5d25e9ab05de841e14208cf365e560f8034d7b008814c4d6b78
|
||||
size 371600
|
||||
3
.plots/hellaswag.png
Normal file
3
.plots/hellaswag.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:359013f9a8358d93b4060396fd569819beb488379a172aec5e1dbeb946a8d634
|
||||
size 350135
|
||||
3
.plots/lambada.png
Normal file
3
.plots/lambada.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:52ab469a00f8dfb75c424d2b2b7572a0a769a9a8345a82b177c6d82a4cf61e58
|
||||
size 378123
|
||||
190
LICENSE
Normal file
190
LICENSE
Normal file
@@ -0,0 +1,190 @@
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
Copyright Nicholas Kluge Corrêa, Shiza Fatimah, Aniket Sen, and Sophia Falk
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
239
README.md
Normal file
239
README.md
Normal file
@@ -0,0 +1,239 @@
|
||||
---
|
||||
language:
|
||||
- pt
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- text-generation-inference
|
||||
datasets:
|
||||
- Polygl0t/gigaverbo-v2
|
||||
- Polygl0t/gigaverbo-v2-synth
|
||||
metrics:
|
||||
- perplexity
|
||||
pipeline_tag: text-generation
|
||||
co2_eq_emissions:
|
||||
emissions: 181000
|
||||
source: CodeCarbon
|
||||
training_type: pre-training
|
||||
geographical_location: Germany
|
||||
hardware_used: NVIDIA A40
|
||||
model-index:
|
||||
- name: GigaVerbo-v2-ablation-EDU-Synth-1.5B
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: ARC Challenge (Portuguese)
|
||||
type: Polygl0t/ARC-poly
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 34.4
|
||||
name: accuracy (normalized)
|
||||
source:
|
||||
url: https://github.com/Nkluge-correa/lm-evaluation-harness
|
||||
name: Language Model Evaluation Harness (branch=polyglot_harness_portuguese)
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (Portuguese)
|
||||
type: Polygl0t/HellaSwag-poly
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 46.0
|
||||
name: accuracy (normalized)
|
||||
source:
|
||||
url: https://github.com/Nkluge-correa/lm-evaluation-harness
|
||||
name: Language Model Evaluation Harness (branch=polyglot_harness_portuguese)
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Calame
|
||||
type: Polygl0t/CALAME-PT
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 57.9
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://github.com/Nkluge-correa/lm-evaluation-harness
|
||||
name: Language Model Evaluation Harness (branch=polyglot_harness_portuguese)
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Lambada (Portuguese)
|
||||
type: Polygl0t/LAMBADA-poly
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 39.0
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://github.com/Nkluge-correa/lm-evaluation-harness
|
||||
name: Language Model Evaluation Harness (branch=polyglot_harness_portuguese)
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Global PIQA (por_latn_braz)
|
||||
type: mrlbenchmarks/global-piqa-nonparallel
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 75.0
|
||||
name: accuracy (normalized)
|
||||
source:
|
||||
url: https://github.com/Nkluge-correa/lm-evaluation-harness
|
||||
name: Language Model Evaluation Harness (branch=polyglot_harness_portuguese)
|
||||
---
|
||||
|
||||
# GigaVerbo-v2-ablation-EDU-Synth-1.5B
|
||||
|
||||
## Model Summary
|
||||
|
||||
**[GigaVerbo-v2-ablation-EDU-Synth-1.5B](https://huggingface.co/Polygl0t/GigaVerbo-v2-ablation-EDU-Synth-1.5B)** is a decoder-transformer natively pretrained in Portuguese. This model is part of an ablation study to measure the impact of our educational data filtering/augmentation strategy on the downstream performance of models trained with [GigaVerbo-v2](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2) and [GigaVerbo-v2-synth](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2-synth). GigaVerbo-v2-ablation-EDU-Synth-1.5B was trained with ~46 billion tokens, those being a mixture of the educational portion of GigaVerbo-v2 (i.e., samples with an Edu Score >= 3) and the synthetic data from GigaVerbo-v2-synth. This model has 1.5 billion parameters and a context length of 4096 tokens.
|
||||
|
||||
## Details
|
||||
|
||||
- **Architecture:** a Transformer-based model ([`llama`](https://huggingface.co/docs/transformers/main/en/model_doc/llama))
|
||||
- **Size:** 1,510,066,176 parameters
|
||||
- **Context length:** 4096 tokens
|
||||
- **Dataset(s):**
|
||||
- [Polygl0t/gigaverbo-v2](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2) (educational subset, Edu Score >= 3)
|
||||
- [Polygl0t/gigaverbo-v2-synth](https://huggingface.co/datasets/Polygl0t/gigaverbo-v2-synth)
|
||||
- **Language(s):** Portuguese
|
||||
- **Batch size:** 2,097,152 tokens
|
||||
- **Number of steps:** 22,000
|
||||
- **GPU:** 16 NVIDIA A40 (48 GB)
|
||||
- **Training time**: ~ 97 hours
|
||||
- **Emissions:** 181 KgCO2 (Germany)
|
||||
- **Total energy consumption:** 477 kWh
|
||||
|
||||
This repository has the [source code](https://github.com/Polygl0t/llm-foundry) used to train this model. The complete configuration used for training is available in the following config file:
|
||||
|
||||
- Single stage (linear warmup with cosine decay): [training_config.yaml](training_config.yaml)
|
||||
|
||||
The main branch of this repository contains the final checkpoint saved at step 22,000. All other checkpoints are available as separate branches. To load a specific checkpoint, you can use the following code snippet:
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_id = "Polygl0t/GigaVerbo-v2-ablation-EDU-Synth-1.5B"
|
||||
revision = "step-2000" # Change this to the desired checkpoint branch
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, revision=revision)
|
||||
```
|
||||
|
||||
Or, you can access all the revisions for the models via the following code snippet:
|
||||
|
||||
```python
|
||||
from huggingface_hub import list_repo_refs
|
||||
out = list_repo_refs("Polygl0t/GigaVerbo-v2-ablation-EDU-Synth-1.5B")
|
||||
branches = [b.name for b in out.branches]
|
||||
print(branches)
|
||||
```
|
||||
|
||||
## Intended Uses
|
||||
|
||||
The primary intended use of this model is to serve as a baseline for evaluating the impact of data quality and filtering on Portuguese language model performance. Researchers and practitioners can use this model as a reference point for further ablation studies or for comparison with other models trained on different data mixtures.
|
||||
|
||||
## Basic usage
|
||||
|
||||
```python
|
||||
from transformers import GenerationConfig, TextGenerationPipeline, AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
# Specify the model and tokenizer
|
||||
model_id = "Polygl0t/GigaVerbo-v2-ablation-EDU-Synth-1.5B"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id)
|
||||
|
||||
# Specify the generation parameters as you like
|
||||
generation_config = GenerationConfig(
|
||||
**{
|
||||
"do_sample": True,
|
||||
"max_new_tokens": 150,
|
||||
"renormalize_logits": True,
|
||||
"repetition_penalty": 1.2,
|
||||
"temperature": 0.1,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"use_cache": True,
|
||||
}
|
||||
)
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
generator = TextGenerationPipeline(model=model, task="text-generation", tokenizer=tokenizer, device=device)
|
||||
|
||||
# Generate text
|
||||
prompt = "A capital de Portugal é"
|
||||
completion = generator(prompt, generation_config=generation_config)
|
||||
print(completion[0]['generated_text'])
|
||||
```
|
||||
|
||||
## Evaluations
|
||||
|
||||
The table below compares our ablation models with checkpoints from the first [Tucano series](https://huggingface.co/TucanoBR). Tucano models are a natural point of comparison because they were trained on Portuguese data of a similar nature and provide multiple checkpoints across different stages of training. To ensure a fair comparison, we select Tucano checkpoints that are closest to our ablation models in terms of both the number of training tokens seen (31B and 52B vs. 46B) and model size (1.1B and 2.4B parameters). We also include additional models for which reliable information on training data volume and model size is available and whose sizes are comparable to our ablation models. Performance is summarized using the NPM (Normalized Performance Metric), which provides a balanced aggregate view across tasks by normalizing each task’s score relative to its random baseline, thereby accounting for differences in task difficulty.
|
||||
|
||||
| | NPM | ARC Challenge | Calame | Global PIQA | HellaSwag | Lambada |
|
||||
| ------------------------------ | ------ | ------------- | ------ | ----------- | --------- | ------- |
|
||||
| GigaVerbo-v2 (EDU) | 39.306 | 0.328 | 0.579 | 0.82 | 0.449 | 0.377 |
|
||||
| Curio-1.1b (1T + 150B) | 39.156 | 0.304 | 0.592 | 0.75 | 0.495 | 0.467 |
|
||||
| Curio-1.1b (1T + 100B) | 38.88 | 0.309 | 0.599 | 0.74 | 0.489 | 0.468 |
|
||||
| Curio-1.1b (1T + 50B) | 38.057 | 0.294 | 0.589 | 0.74 | 0.48 | 0.469 |
|
||||
| GigaVerbo-v2 (EDU+Synth) | 37.49 | 0.344 | 0.579 | 0.75 | 0.46 | 0.39 |
|
||||
| Curio-edu-1b1 (1T + 20B) | 34.774 | 0.322 | 0.549 | 0.69 | 0.463 | 0.429 |
|
||||
| GigaVerbo-v2 (Synth) | 33.864 | 0.326 | 0.561 | 0.72 | 0.439 | 0.339 |
|
||||
| Tucano-2b4 (500B) | 33.551 | 0.304 | 0.503 | 0.73 | 0.488 | 0.324 |
|
||||
| Tucano-1b1 (250B) | 29.124 | 0.301 | 0.489 | 0.68 | 0.441 | 0.284 |
|
||||
| Llama-3.2-1B (9T) | 28.315 | 0.317 | 0.5 | 0.55 | 0.453 | 0.456 |
|
||||
| GigaVerbo-v2 (NonEDU) | 28.049 | 0.256 | 0.565 | 0.65 | 0.383 | 0.352 |
|
||||
| Tucano-2b4 (52B) | 27.433 | 0.274 | 0.456 | 0.71 | 0.412 | 0.248 |
|
||||
| GlorIA-1.3B (35B) | 27.274 | 0.264 | 0.547 | 0.64 | 0.364 | 0.367 |
|
||||
| Carvalho_pt-gl-1.3B (26B + 5B) | 26.746 | 0.27 | 0.534 | 0.63 | 0.385 | 0.336 |
|
||||
| Tucano-1b1 (52B) | 24.927 | 0.284 | 0.464 | 0.64 | 0.401 | 0.257 |
|
||||
|
||||
### ⭐ GigaVerbo-v2 Ablations: The Impact of 46B Tokens of Educational & Synthetic Data ⭐
|
||||
|
||||
All individual benchmark scores and their evolution across training time can be found in the [.plots](https://huggingface.co/Polygl0t/GigaVerbo-v2-ablation-EDU-Synth-1.5B/tree/main/.plots) folder.
|
||||
|
||||
|
||||
|
||||
## Cite as 🤗
|
||||
|
||||
```latex
|
||||
@misc{correa2026tucano2cool,
|
||||
title={{Tucano 2 Cool: Better Open Source LLMs for Portuguese}},
|
||||
author={Nicholas Kluge Corr{\^e}a and Aniket Sen and Shiza Fatimah and Sophia Falk and Lennard Landgraf and Julia Kastner and Lucie Flek},
|
||||
year={2026},
|
||||
eprint={2603.03543},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2603.03543},
|
||||
}
|
||||
```
|
||||
|
||||
## Aknowlegments
|
||||
|
||||
Polyglot is a project funded by the Federal Ministry of Education and Research (BMBF) and the Ministry of Culture and Science of the State of North Rhine-Westphalia (MWK) as part of TRA Sustainable Futures (University of Bonn) and the Excellence Strategy of the federal and state governments.
|
||||
|
||||
We also gratefully acknowledge the granted access to the [Marvin cluster](https://www.hpc.uni-bonn.de/en/systems/marvin) hosted by [University of Bonn](https://www.uni-bonn.de/en) along with the support provided by its High Performance Computing & Analytics Lab.
|
||||
|
||||
## License
|
||||
|
||||
This model is licensed under the Apache License, Version 2.0. For more details, see the [LICENSE](LICENSE) file.
|
||||
45
added_tokens.json
Normal file
45
added_tokens.json
Normal file
@@ -0,0 +1,45 @@
|
||||
{
|
||||
" ": 49151,
|
||||
" ": 49150,
|
||||
" ": 49149,
|
||||
" ": 49148,
|
||||
" ": 49147,
|
||||
" ": 49146,
|
||||
" ": 49145,
|
||||
" ": 49144,
|
||||
" ": 49143,
|
||||
" ": 49142,
|
||||
" ": 49141,
|
||||
" ": 49140,
|
||||
" ": 49139,
|
||||
" ": 49138,
|
||||
" ": 49137,
|
||||
" ": 49136,
|
||||
" ": 49135,
|
||||
" ": 49134,
|
||||
" ": 49133,
|
||||
" ": 49132,
|
||||
" ": 49131,
|
||||
" ": 49130,
|
||||
" ": 49129,
|
||||
"</answer>": 49119,
|
||||
"</context>": 49121,
|
||||
"</think>": 49117,
|
||||
"</tool_call>": 49113,
|
||||
"</tool_response>": 49115,
|
||||
"</tools>": 49111,
|
||||
"<answer>": 49118,
|
||||
"<context>": 49120,
|
||||
"<think>": 49116,
|
||||
"<tool_call>": 49112,
|
||||
"<tool_response>": 49114,
|
||||
"<tools>": 49110,
|
||||
"<|fim_middle|>": 49124,
|
||||
"<|fim_prefix|>": 49122,
|
||||
"<|fim_suffix|>": 49123,
|
||||
"<|image_pad|>": 49127,
|
||||
"<|image_placeholder|>": 49128,
|
||||
"<|image|>": 49126,
|
||||
"<|pad|>": 49109,
|
||||
"<|repo_name|>": 49125
|
||||
}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"is_llama_config": true,
|
||||
"max_position_embeddings": 4096,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 49109,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_interleaved": false,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 50000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.53.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
14
emissions.csv
Normal file
14
emissions.csv
Normal file
@@ -0,0 +1,14 @@
|
||||
timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
||||
2025-11-22T06:25:09,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,31613.25393096404,8.244000432349367,0.0002607767125254,45.149149674,990.422086979608,70.0,0.3818124452351561,20.666380868647025,0.592443075012357,21.64063638889452,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-22T06:27:39,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,31763.76656902908,8.282828623079931,0.0002607634269405,45.13924048500001,1142.4038799168777,70.0,0.3836236955007326,20.76368359121136,0.5952537398791597,21.74256102659124,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-22T15:14:54,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,63398.30358983506,16.532553451641128,0.0002607728048782,45.12735640125,795.3632607415248,70.0,0.7657098640601526,41.444393594377246,1.188120591020942,43.39822404945827,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-23T00:02:14,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,95038.66005746904,24.7832615000595,0.0002607703168907,45.12421380375,1446.7715163215078,70.0,1.147851850187794,62.12753554032199,1.781080650071727,65.05646804058144,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-23T08:49:30,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,126674.16578492313,33.03409715828668,0.0002607800647716,45.1401727275,1449.290254627998,70.0,1.5299399141526429,82.81114845053247,2.37395864486144,86.71504700954634,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-23T17:36:58,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,158322.43852378102,41.28775047568845,0.0002607826841265,45.140673834000005,973.4895098589632,70.0,1.912154550599929,103.50183486945724,2.9670329600150573,108.38102238007204,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-24T02:24:41,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,189985.21572616813,49.54274855845636,0.0002607715993536,45.139323105,787.5901252836825,70.0,2.294550483723609,124.19558981944812,3.560387478575368,130.05052778174658,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-24T11:12:23,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,221647.29003088103,57.79818881727106,0.0002607665034353,45.12356587384616,1702.119271961065,70.0,2.676947538738762,144.89050208953142,4.153744274529637,151.72119390279843,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-24T19:59:59,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,253303.509333228,66.05204632445293,0.0002607624604109,45.118873305,777.4485655161078,70.0,3.059284840430322,165.58141245030248,4.747007984116654,173.3877052748469,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-25T04:47:42,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,284966.4849852461,74.30596612128329,0.0002607533518376,45.10885245750001,805.4063298716145,70.0,3.44169365517518,186.27230425939203,5.34038224367986,195.0543801582446,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-25T13:44:10,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,317154.8521652941,82.60549506125449,0.0002604579261432,45.10126903500001,798.3456038798357,70.0,3.8304807404871872,207.0666529637467,5.943646086435737,216.84077979066672,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-25T22:33:40,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,348924.35933438595,90.86642378495516,0.0002604186877588,45.115749529615385,1753.844439453577,70.0,4.214187083996457,227.77263671102057,6.539029427076008,238.5258532220899,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
2025-11-25T22:36:25,Polyglot,1ac22d0b-b416-4d5f-9003-a43345d296ac,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,349089.98651392804,90.90932306568932,0.0002604180199309,0.0,1852.123454506777,70.0,4.21618062071518,227.87987977209275,6.542404145033048,238.63846453783785,Germany,DEU,north rhine-westphalia,,,Linux-5.14.0-570.35.1.el9_6.x86_64-x86_64-with-glibc2.34,3.12.3,3.0.4,256,AMD EPYC 7713 64-Core Processor,8,8 x NVIDIA A40,7.1178,50.7246,975,machine,N,1.0
|
||||
|
190
evals.yaml
Normal file
190
evals.yaml
Normal file
@@ -0,0 +1,190 @@
|
||||
evaluations:
|
||||
arc_challenge_poly_pt_acc: 0.30085470085470084
|
||||
arc_challenge_poly_pt_acc_norm: 0.3435897435897436
|
||||
arc_challenge_poly_pt_acc_norm_stderr: 0.013889944781406437
|
||||
arc_challenge_poly_pt_acc_stderr: 0.01341389388061822
|
||||
arc_challenge_poly_pt_alias: arc_challenge_poly_pt
|
||||
assin2_rte_acc,all: 0.5024509803921569
|
||||
assin2_rte_acc_stderr,all: 0.007142229345039623
|
||||
assin2_rte_alias: assin2_rte
|
||||
assin2_rte_f1_macro,all: 0.34088811077510744
|
||||
assin2_rte_f1_macro_stderr,all: 0.0036977314980645975
|
||||
assin2_sts_alias: assin2_sts
|
||||
assin2_sts_mse,all: 2.584869281045752
|
||||
assin2_sts_mse_stderr,all: N/A
|
||||
assin2_sts_pearson,all: 0.020246144461495013
|
||||
assin2_sts_pearson_stderr,all: 0.012848574237206775
|
||||
assin_entailment_acc: 0.62075
|
||||
assin_entailment_acc_stderr: 0.007672651221656846
|
||||
assin_entailment_alias: assin_entailment
|
||||
assin_paraphrase_acc: 0.59675
|
||||
assin_paraphrase_acc_stderr: 0.007757248423299025
|
||||
assin_paraphrase_alias: assin_paraphrase
|
||||
belebele_por_Latn_acc: 0.22666666666666666
|
||||
belebele_por_Latn_acc_norm: 0.22666666666666666
|
||||
belebele_por_Latn_acc_norm_stderr: 0.013963598349030474
|
||||
belebele_por_Latn_acc_stderr: 0.013963598349030474
|
||||
belebele_por_Latn_alias: belebele_por_Latn
|
||||
bluex_acc,all: 0.2698191933240612
|
||||
bluex_acc,exam_id__UNICAMP_2018: 0.3333333333333333
|
||||
bluex_acc,exam_id__UNICAMP_2019: 0.3
|
||||
bluex_acc,exam_id__UNICAMP_2020: 0.3090909090909091
|
||||
bluex_acc,exam_id__UNICAMP_2021_1: 0.2391304347826087
|
||||
bluex_acc,exam_id__UNICAMP_2021_2: 0.3333333333333333
|
||||
bluex_acc,exam_id__UNICAMP_2022: 0.3076923076923077
|
||||
bluex_acc,exam_id__UNICAMP_2023: 0.3023255813953488
|
||||
bluex_acc,exam_id__UNICAMP_2024: 0.3333333333333333
|
||||
bluex_acc,exam_id__USP_2018: 0.25925925925925924
|
||||
bluex_acc,exam_id__USP_2019: 0.225
|
||||
bluex_acc,exam_id__USP_2020: 0.17857142857142858
|
||||
bluex_acc,exam_id__USP_2021: 0.25
|
||||
bluex_acc,exam_id__USP_2022: 0.2653061224489796
|
||||
bluex_acc,exam_id__USP_2023: 0.20454545454545456
|
||||
bluex_acc,exam_id__USP_2024: 0.1951219512195122
|
||||
bluex_acc_stderr,all: 0.009522448695577326
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2018: 0.03694964333964267
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2019: 0.03747275630361617
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2020: 0.035904653645853185
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2021_1: 0.036254833462246665
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2021_2: 0.038008168468976235
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2022: 0.042742868943786344
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2023: 0.040341644184605924
|
||||
bluex_acc_stderr,exam_id__UNICAMP_2024: 0.04053327096189869
|
||||
bluex_acc_stderr,exam_id__USP_2018: 0.0344262177569184
|
||||
bluex_acc_stderr,exam_id__USP_2019: 0.038146963606575296
|
||||
bluex_acc_stderr,exam_id__USP_2020: 0.029536187641256872
|
||||
bluex_acc_stderr,exam_id__USP_2021: 0.03461792391082892
|
||||
bluex_acc_stderr,exam_id__USP_2022: 0.036410693630710485
|
||||
bluex_acc_stderr,exam_id__USP_2023: 0.03508480264125641
|
||||
bluex_acc_stderr,exam_id__USP_2024: 0.03582337589286989
|
||||
bluex_alias: bluex
|
||||
calame_pt_acc: 0.5789980732177264
|
||||
calame_pt_acc_stderr: 0.010838559109941895
|
||||
calame_pt_alias: calame_pt
|
||||
calame_pt_perplexity: 7.1322676051739915
|
||||
calame_pt_perplexity_stderr: 0.41447318920967197
|
||||
enem_challenge_acc,all: 0.198740377886634
|
||||
enem_challenge_acc,exam_id__2009: 0.2
|
||||
enem_challenge_acc,exam_id__2010: 0.21367521367521367
|
||||
enem_challenge_acc,exam_id__2011: 0.2222222222222222
|
||||
enem_challenge_acc,exam_id__2012: 0.2672413793103448
|
||||
enem_challenge_acc,exam_id__2013: 0.21296296296296297
|
||||
enem_challenge_acc,exam_id__2014: 0.1743119266055046
|
||||
enem_challenge_acc,exam_id__2015: 0.16806722689075632
|
||||
enem_challenge_acc,exam_id__2016: 0.18181818181818182
|
||||
enem_challenge_acc,exam_id__2016_2: 0.2032520325203252
|
||||
enem_challenge_acc,exam_id__2017: 0.21551724137931033
|
||||
enem_challenge_acc,exam_id__2022: 0.19548872180451127
|
||||
enem_challenge_acc,exam_id__2023: 0.14074074074074075
|
||||
enem_challenge_acc_stderr,all: 0.00610558911077106
|
||||
enem_challenge_acc_stderr,exam_id__2009: 0.02154694204401486
|
||||
enem_challenge_acc_stderr,exam_id__2010: 0.021865515933679015
|
||||
enem_challenge_acc_stderr,exam_id__2011: 0.022195336485659214
|
||||
enem_challenge_acc_stderr,exam_id__2012: 0.02374992962172603
|
||||
enem_challenge_acc_stderr,exam_id__2013: 0.02269408166705055
|
||||
enem_challenge_acc_stderr,exam_id__2014: 0.020897673936382765
|
||||
enem_challenge_acc_stderr,exam_id__2015: 0.019802918239207434
|
||||
enem_challenge_acc_stderr,exam_id__2016: 0.020291042922884254
|
||||
enem_challenge_acc_stderr,exam_id__2016_2: 0.020969856982989393
|
||||
enem_challenge_acc_stderr,exam_id__2017: 0.02203067864108359
|
||||
enem_challenge_acc_stderr,exam_id__2022: 0.019840331274268017
|
||||
enem_challenge_acc_stderr,exam_id__2023: 0.017323886319225976
|
||||
enem_challenge_alias: enem
|
||||
faquad_nli_acc,all: 0.7753846153846153
|
||||
faquad_nli_acc_stderr,all: 0.011564640936900579
|
||||
faquad_nli_alias: faquad_nli
|
||||
faquad_nli_f1_macro,all: 0.43674176776429807
|
||||
faquad_nli_f1_macro_stderr,all: 0.0036705611888408394
|
||||
global_piqa_completions_por_latn_braz_acc: 0.78
|
||||
global_piqa_completions_por_latn_braz_acc_bytes: 0.76
|
||||
global_piqa_completions_por_latn_braz_acc_bytes_stderr: 0.04292346959909278
|
||||
global_piqa_completions_por_latn_braz_acc_norm: 0.75
|
||||
global_piqa_completions_por_latn_braz_acc_norm_stderr: 0.04351941398892446
|
||||
global_piqa_completions_por_latn_braz_acc_stderr: 0.041633319989322654
|
||||
global_piqa_completions_por_latn_braz_alias: global_piqa_completions_por_latn_braz
|
||||
hatebr_offensive_acc,all: 0.5457142857142857
|
||||
hatebr_offensive_acc_stderr,all: 0.009408906567694409
|
||||
hatebr_offensive_alias: hatebr_offensive_binary
|
||||
hatebr_offensive_f1_macro,all: 0.4508029478016081
|
||||
hatebr_offensive_f1_macro_stderr,all: 0.008913031329806937
|
||||
hellaswag_poly_pt_acc: 0.361469281612309
|
||||
hellaswag_poly_pt_acc_norm: 0.4601798678079965
|
||||
hellaswag_poly_pt_acc_norm_stderr: 0.0051884131715642335
|
||||
hellaswag_poly_pt_acc_stderr: 0.005001183649049966
|
||||
hellaswag_poly_pt_alias: hellaswag_poly_pt
|
||||
lambada_poly_pt_acc: 0.3904521637880846
|
||||
lambada_poly_pt_acc_stderr: 0.0067967279472032245
|
||||
lambada_poly_pt_alias: lambada_poly_pt
|
||||
lambada_poly_pt_perplexity: 20.774403141688516
|
||||
lambada_poly_pt_perplexity_stderr: 0.7231795341389268
|
||||
mmlu_poly_pt_acc: 0.26208345842089464
|
||||
mmlu_poly_pt_acc_stderr: 0.0038099775311724042
|
||||
mmlu_poly_pt_alias: mmlu_poly_pt
|
||||
oab_exams_acc,all: 0.2610478359908884
|
||||
oab_exams_acc,exam_id__2010-01: 0.23529411764705882
|
||||
oab_exams_acc,exam_id__2010-02: 0.27
|
||||
oab_exams_acc,exam_id__2011-03: 0.2727272727272727
|
||||
oab_exams_acc,exam_id__2011-04: 0.275
|
||||
oab_exams_acc,exam_id__2011-05: 0.2625
|
||||
oab_exams_acc,exam_id__2012-06: 0.2625
|
||||
oab_exams_acc,exam_id__2012-06a: 0.225
|
||||
oab_exams_acc,exam_id__2012-07: 0.275
|
||||
oab_exams_acc,exam_id__2012-08: 0.25
|
||||
oab_exams_acc,exam_id__2012-09: 0.35064935064935066
|
||||
oab_exams_acc,exam_id__2013-10: 0.275
|
||||
oab_exams_acc,exam_id__2013-11: 0.2875
|
||||
oab_exams_acc,exam_id__2013-12: 0.25
|
||||
oab_exams_acc,exam_id__2014-13: 0.25
|
||||
oab_exams_acc,exam_id__2014-14: 0.275
|
||||
oab_exams_acc,exam_id__2014-15: 0.32051282051282054
|
||||
oab_exams_acc,exam_id__2015-16: 0.1875
|
||||
oab_exams_acc,exam_id__2015-17: 0.2948717948717949
|
||||
oab_exams_acc,exam_id__2015-18: 0.175
|
||||
oab_exams_acc,exam_id__2016-19: 0.24358974358974358
|
||||
oab_exams_acc,exam_id__2016-20: 0.25
|
||||
oab_exams_acc,exam_id__2016-20a: 0.2875
|
||||
oab_exams_acc,exam_id__2016-21: 0.2625
|
||||
oab_exams_acc,exam_id__2017-22: 0.25
|
||||
oab_exams_acc,exam_id__2017-23: 0.2125
|
||||
oab_exams_acc,exam_id__2017-24: 0.275
|
||||
oab_exams_acc,exam_id__2018-25: 0.275
|
||||
oab_exams_acc_stderr,all: 0.005404522993204322
|
||||
oab_exams_acc_stderr,exam_id__2010-01: 0.026605455313616685
|
||||
oab_exams_acc_stderr,exam_id__2010-02: 0.025613225623037045
|
||||
oab_exams_acc_stderr,exam_id__2011-03: 0.025797748277668113
|
||||
oab_exams_acc_stderr,exam_id__2011-04: 0.028905026152293026
|
||||
oab_exams_acc_stderr,exam_id__2011-05: 0.0283315547675685
|
||||
oab_exams_acc_stderr,exam_id__2012-06: 0.028401435522187126
|
||||
oab_exams_acc_stderr,exam_id__2012-06a: 0.02692493002179001
|
||||
oab_exams_acc_stderr,exam_id__2012-07: 0.028685143633187495
|
||||
oab_exams_acc_stderr,exam_id__2012-08: 0.02792646945667252
|
||||
oab_exams_acc_stderr,exam_id__2012-09: 0.03143226713819032
|
||||
oab_exams_acc_stderr,exam_id__2013-10: 0.028749520581305216
|
||||
oab_exams_acc_stderr,exam_id__2013-11: 0.029216602612826752
|
||||
oab_exams_acc_stderr,exam_id__2013-12: 0.02799652135475067
|
||||
oab_exams_acc_stderr,exam_id__2014-13: 0.027941364058848093
|
||||
oab_exams_acc_stderr,exam_id__2014-14: 0.028700665742904995
|
||||
oab_exams_acc_stderr,exam_id__2014-15: 0.0304707537714559
|
||||
oab_exams_acc_stderr,exam_id__2015-16: 0.025187032117302378
|
||||
oab_exams_acc_stderr,exam_id__2015-17: 0.0297749047613837
|
||||
oab_exams_acc_stderr,exam_id__2015-18: 0.02449033420128714
|
||||
oab_exams_acc_stderr,exam_id__2016-19: 0.028105853302671797
|
||||
oab_exams_acc_stderr,exam_id__2016-20: 0.02785679771062364
|
||||
oab_exams_acc_stderr,exam_id__2016-20a: 0.029237922790613942
|
||||
oab_exams_acc_stderr,exam_id__2016-21: 0.028334176853691478
|
||||
oab_exams_acc_stderr,exam_id__2017-22: 0.027945788844504417
|
||||
oab_exams_acc_stderr,exam_id__2017-23: 0.026388686173944978
|
||||
oab_exams_acc_stderr,exam_id__2017-24: 0.02882934165027393
|
||||
oab_exams_acc_stderr,exam_id__2018-25: 0.02893736358130262
|
||||
oab_exams_alias: oab_exams
|
||||
portuguese_hate_speech_acc,all: 0.700352526439483
|
||||
portuguese_hate_speech_acc_stderr,all: 0.011075616750882897
|
||||
portuguese_hate_speech_alias: portuguese_hate_speech_binary
|
||||
portuguese_hate_speech_f1_macro,all: 0.4118866620594333
|
||||
portuguese_hate_speech_f1_macro_stderr,all: 0.0038311957825553846
|
||||
tweetsentbr_acc,all: 0.3373134328358209
|
||||
tweetsentbr_acc_stderr,all: 0.0074549865355581415
|
||||
tweetsentbr_alias: tweetsentbr
|
||||
tweetsentbr_f1_macro,all: 0.21837645526737784
|
||||
tweetsentbr_f1_macro_stderr,all: 0.005256512662126685
|
||||
step: 22000
|
||||
12
evals_all_steps.csv
Normal file
12
evals_all_steps.csv
Normal file
File diff suppressed because one or more lines are too long
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 49109,
|
||||
"transformers_version": "4.53.2",
|
||||
"do_sample": true,
|
||||
"max_new_tokens": 1024,
|
||||
"renormalize_logits": true,
|
||||
"repetition_penalty": 1.2,
|
||||
"temperature": 0.1,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"use_cache": false
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fda2d734bb76f28879a3801e865eb05c4e5ce8093a97080552bfd7180777dbc1
|
||||
size 3020161696
|
||||
74
special_tokens_map.json
Normal file
74
special_tokens_map.json
Normal file
@@ -0,0 +1,74 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<tools>",
|
||||
"</tools>",
|
||||
"<tool_call>",
|
||||
"</tool_call>",
|
||||
"<tool_response>",
|
||||
"</tool_response>",
|
||||
"<think>",
|
||||
"</think>",
|
||||
"<answer>",
|
||||
"</answer>",
|
||||
"<context>",
|
||||
"</context>",
|
||||
"<|fim_prefix|>",
|
||||
"<|fim_suffix|>",
|
||||
"<|fim_middle|>",
|
||||
"<|repo_name|>",
|
||||
"<|image|>",
|
||||
"<|image_pad|>",
|
||||
"<|image_placeholder|>",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" "
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|unk|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
463711
tokenizer.json
Normal file
463711
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
441
tokenizer_config.json
Normal file
441
tokenizer_config.json
Normal file
@@ -0,0 +1,441 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": null,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|unk|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49109": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49110": {
|
||||
"content": "<tools>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49111": {
|
||||
"content": "</tools>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49112": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49113": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49114": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49115": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49116": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49117": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49118": {
|
||||
"content": "<answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49119": {
|
||||
"content": "</answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49120": {
|
||||
"content": "<context>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49121": {
|
||||
"content": "</context>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49122": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49123": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49124": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49125": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49126": {
|
||||
"content": "<|image|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49127": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49128": {
|
||||
"content": "<|image_placeholder|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49129": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49130": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49131": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49132": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49133": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49134": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49135": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49136": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49137": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49138": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49139": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49140": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49141": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49142": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49143": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49144": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49145": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49146": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49147": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49148": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49149": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49150": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"49151": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<tools>",
|
||||
"</tools>",
|
||||
"<tool_call>",
|
||||
"</tool_call>",
|
||||
"<tool_response>",
|
||||
"</tool_response>",
|
||||
"<think>",
|
||||
"</think>",
|
||||
"<answer>",
|
||||
"</answer>",
|
||||
"<context>",
|
||||
"</context>",
|
||||
"<|fim_prefix|>",
|
||||
"<|fim_suffix|>",
|
||||
"<|fim_middle|>",
|
||||
"<|repo_name|>",
|
||||
"<|image|>",
|
||||
"<|image_pad|>",
|
||||
"<|image_placeholder|>",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" ",
|
||||
" "
|
||||
],
|
||||
"bos_token": "<|im_start|>",
|
||||
"bos_token_id": 1,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"eos_token_id": 2,
|
||||
"extra_special_tokens": {},
|
||||
"legacy": false,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<|pad|>",
|
||||
"pad_token_id": 49109,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "PreTrainedTokenizerFast",
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"truncation_side": "right",
|
||||
"unk_token": "<|unk|>",
|
||||
"unk_token_id": 0,
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
3
train_logs.parquet
Normal file
3
train_logs.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4f0275584942d7168c2a567102d7d8d4deb373ed3d648fb6ad601179533bcd0
|
||||
size 789483
|
||||
88
training_config.yaml
Normal file
88
training_config.yaml
Normal file
@@ -0,0 +1,88 @@
|
||||
# Directory settings
|
||||
checkpoint_dir: "/lustre/mlnvme/data/polyglot/portuguese/checkpoints/models/ablations/gigaverbo-edu"
|
||||
train_dataset_dir:
|
||||
# Total: ~50B
|
||||
- /lustre/mlnvme/data/polyglot/portuguese/mix_edu
|
||||
val_dataset_dir: "/lustre/mlnvme/data/polyglot/portuguese/mix_edu_val"
|
||||
dataset_type: "parquet"
|
||||
cache_dir: "/lustre/mlnvme/data/polyglot/.cache"
|
||||
|
||||
# Data loading settings
|
||||
pin_memory: true
|
||||
num_workers_for_dataloader: 8
|
||||
shuffle_dataset: true
|
||||
mask_eos_token: false
|
||||
mask_pad_token: false
|
||||
|
||||
# Model architecture settings
|
||||
vocab_size: 49152
|
||||
num_hidden_layers: 28
|
||||
num_attention_heads: 16
|
||||
num_key_value_heads: 8
|
||||
head_dim: 128
|
||||
hidden_size: 2048
|
||||
intermediate_size: 6144
|
||||
max_position_embeddings: 4096
|
||||
tie_word_embeddings: true
|
||||
hidden_act: "silu"
|
||||
output_hidden_states: false
|
||||
attn_implementation: "flash_attention_2"
|
||||
use_cache: false
|
||||
no_rope_layer_interval: null
|
||||
rope_theta: 50000.0
|
||||
rope_scale_factor: null
|
||||
rms_norm_eps: 0.000001
|
||||
|
||||
# Training settings
|
||||
total_batch_size: 2097152
|
||||
micro_batch_size: 4
|
||||
eval_micro_batch_size: 2
|
||||
num_train_epochs: 1
|
||||
warmup_steps: 2000
|
||||
max_learning_rate: 0.0008
|
||||
min_learning_rate: 0.0
|
||||
muon_learning_rate: 0.008
|
||||
weight_decay: 0.1
|
||||
beta1: 0.9
|
||||
beta2: 0.95
|
||||
eps: 0.00000001
|
||||
lr_decay_type: "cosine"
|
||||
use_sqrt: false
|
||||
lr_decay_iters_coef: 1.0
|
||||
seed: 1337
|
||||
max_steps: 22000
|
||||
max_grad_norm: 1.0
|
||||
|
||||
# Precision and optimization settings
|
||||
torch_compile: false
|
||||
mat_mul_precision: "highest"
|
||||
tf32: true
|
||||
bf16: true
|
||||
gradient_checkpointing: false
|
||||
use_liger_kernel: true
|
||||
static_graph: false
|
||||
|
||||
# Hub settings
|
||||
push_to_hub: false
|
||||
hub_token: null
|
||||
hub_model_id: null
|
||||
|
||||
# Tokenizer and Reference model
|
||||
tokenizer_name_or_path: "/lustre/mlnvme/data/polyglot/portuguese/checkpoints/tokenizers/sp-bpe"
|
||||
chat_template_path: null
|
||||
reference_model: "HuggingFaceTB/SmolLM2-360M"
|
||||
continual_pretraining: false
|
||||
|
||||
# Checkpoint settings
|
||||
resume_from_checkpoint: null
|
||||
checkpointing_steps: 2000
|
||||
begin_new_stage: false
|
||||
stage_name: "single_cosine"
|
||||
|
||||
# Miscellaneous settings
|
||||
sanity_check: false
|
||||
sanity_check_num_samples: 100000
|
||||
wandb_token: null
|
||||
wandb_id: "gigaverbo-edu-ablation"
|
||||
wandb_project: "Polyglot"
|
||||
wandb_desc: "Developing LLMs for low-resource languages"
|
||||
3
val_logs.parquet
Normal file
3
val_logs.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4ece97549df74776982e3c3523be9ae4b7f036455207b692b03bdc2ad302214a
|
||||
size 2268
|
||||
Reference in New Issue
Block a user